1,515 research outputs found
Diffusion MRI Allows Capturing the Amyloid-β and τ Proteins Status in Alzheimer’s Disease Continuum
No full textAlzheimer's Disease (AD) is a neurodegenerative process characterized by the accumulation of amyloid-β (Aβ) and tau (τ) proteins leading to neurodegeneration. It has been hypothesizes that the aggregation of these proteins could spread through specific white matter (WM) pathways. To investigate such hypothesis, convolutional neural networks were employed to analyze microstructural alterations induced by the accumulation of Aβ and τ proteins via two classification tasks, relying on mean diffusivity (MD) and fractional anisotropy (FA), achieving competitive performance. A post-hoc analysis via integrated gradients revealed that the splenium of the corpus callosum played a prominent role for both indices, while index-specific were the ventricles and subcortical regions for MD and the corticospinal tract for FA. This supports the assumption that WM pathways might play a key role in misfolded protein distribution and highlights the potential of diffusion imaging for the identification of Aβ and τ proteins spread and accumulation
Objective Assessment of the Bias Introduced by Baseline Signals in XAI Attribution Methods
No full textThis work represents a first step towards a systematic analysis of the impact of the choice of the baseline signals to be used in explainable baseline-dependent methods for multi-modal and multi-dimensional data relying on single-input deep networks, in view of the generalization to multi -channel architectures. This point is critical for ensuring the soundness of the attribution values and enabling their subsequent validation through association studies. In this work, two different CNNs were implemented to predict Alzheimer's disease patients from control subjects using structural Magnetic Resonance Imaging volumes and genetics data. The Integrated Gradients method was applied to both models for post-hoc attribution visualization relying on different baselines. Differences in the attribution maps were found with respect to the attributions of the reference baseline in both modalities highlighting the importance of finding and using the 'optimal' baseline. We believe this work is highly relevant for the community in the framework of the validation of XAI post-hoc methods, as it provides evidence of the impact of the choice of the baselines for deriving feature attribution values with the Integrated Gradients method which determines the reliability of the outcomes, improving both the awareness of the users and their trust in the methods
Sharing privacy-sensitive access to neuroimaging and genetics data: a review and preliminary validation
No full textThe growth of data sharing initiatives for neuroimaging and genomics represents an exciting opportunity to confront the “small N” problem that plagues contemporary neuroimaging studies while further understanding the role genetic markers play in the function of the brain. When it is possible, open data sharing provides the most benefits. However, some data cannot be shared at all due to privacy concerns and/or risk of re-identification. Sharing other data sets is hampered by the proliferation of complex data use agreements (DUAs) which preclude truly automated data mining. These DUAs arise because of concerns about the privacy and confidentiality for subjects; though many do permit direct access to data, they often require a cumbersome approval process that can take months. An alternative approach is to only share data derivatives such as statistical summaries—the challenges here are to reformulate computational methods to quantify the privacy risks associated with sharing the results of those computations. For example, a derived map of gray matter is often as identifiable as a fingerprint. Thus alternative approaches to accessing data are needed. This paper reviews the relevant literature on differential privacy, a framework for measuring and tracking privacy loss in these settings, and demonstrates the feasibility of using this framework to calculate statistics on data distributed at many sites while still providing privacy.This document is protected by copyright and was first published by Frontiers. All rights reserved. It is reproduced with permission.Peer reviewe
Decentralized temporal independent component analysis: leveraging fMRI data in collaborative settings
No full textPeer reviewe
A deep generative multimodal imaging genomics framework for Alzheimer's disease prediction
No full textAlzheimer's disease (AD) is a neurodegenerative process characterized by the accumulation of amyloid-beta plaques and neurofibrillary tangles and is the most common cause of dementia. Studies have been striving to analyze the disease using available physiological and behavioral data. Functional/structural neuroimaging and genomics are complementary modalities for exploring the mechanisms subserving the development of AD. In this paper, we present a deep multimodal generative data fusion framework for integrating these sources in a classification task involving AD patients and healthy controls from the ADNI database. Biological data fusion has the potential to improve the fmal prediction, but at the same time, it is particularly challenging due to the unavailability of all sources of input for the entire cohort of subjects. Our proposed model allows us to perform prediction even if individuals are missing certain modalities. Our method addresses the missing modalities problem via knowledge transfer from two generative adversarial networks. The model exhibits superior performance for predicting AD versus healthy control, even with missing modalities. This could have an important impact from the patient point of view since certain clinical tests may not be necessary or available to a given individual
Prediction of human errors by maladaptive changes in event-related brain networks
No full textHumans engaged in monotonous tasks are susceptible to occasional errors that may lead to serious consequences, but little is known about brain activity patterns preceding errors. Using functional MRI and applying independent component analysis followed by deconvolution of hemodynamic responses, we studied error preceding brain activity on a trial-by-trial basis. We found a set of brain regions in which the temporal evolution of activation predicted performance errors. These maladaptive brain activity changes started to evolve approximately 30 sec before the error. In particular, a coincident decrease of deactivation in default mode regions of the brain, together with a decline of activation in regions associated with maintaining task effort, raised the probability of future errors. Our findings provide insights into the brain network dynamics preceding human performance errors and suggest that monitoring of the identified precursor states may help in avoiding human errors in critical real-world situation
The Fast and the Curious: Dissecting the Relationship between Dynamic Functional Connectivity and Information Processing Speed
No full textInformation processing speed (IPS) is a foundational cognitive skill that is vital for daily functioning. Changes in IPS are common in several medical conditions and in aging, supporting the need to understand the biological basis of these changes. Dynamic functional network connectivity (dFNC) is a relatively new functional magnetic resonance imaging method designed to estimate time-sensitive fluctuations in network-level connectivity patterns. Previous work investigating dFNC and IPS has suggested that dFNC may be a useful tool for investigating neurobiological models of IPS. However, there are considerable gaps in the literature, including the method of IPS estimation, sample representation, and size. Therefore, this study tested the relationship between dFNC measures and IPS. Neurotypical individuals were selected from the UK Biobank study (n=16831). Reaction time, symbol digit substitution, and trail-making tasks were used as estimates of IPS. IPS was quantified with raw, normed, and indexed scores. A sliding window approach with k-means clustering identified four dFNC states. Multiple linear regressions tested the relationship between IPS estimates and state-specific metrics. Significant associations were found between multiple state metrics and the three IPS measures. Findings generally align with prior work, including strong associations with time spent in highly connected visual and subcortical brain states. Findings also demonstrate consistency between raw and normed results. In sum, the findings further the literature by addressing questions about IPS estimation, sample size, and cohort biases. Future work addressing questions about scan and IPS acquisition methods are needed.Ph
Brain connectomics : time for a molecular imaging perspective?
No full textIn the past two decades brain connectomics has evolved into a major concept in neuroscience. However, the current perspective on brain connectivity and how it underpins brain function relies mainly on the hemodynamic signal of functional magnetic resonance imaging (MRI). Molecular imaging provides unique information inaccessible to MRI-based and electrophysiological techniques. Thus, positron emission tomography (PET) has been successfully applied to measure neural activity, neurotransmission, and proteinopathies in normal and pathological cognition. Here, we position molecular imaging within the brain connectivity framework from the perspective of timeliness, validity, reproducibility, and resolution. We encourage the neuroscientific community to take an integrative approach whereby MRI-based, electrophysiological techniques, and molecular imaging contribute to our understanding of the brain connectome
Structure/function interrelationships in patients with schizophrenia who have persistent auditory verbal hallucinations: A multimodal MRI study using parallel ICA
No full textLandslide risk reduction in Wasco County, Oregon
No full textby William J. Burns, Nancy Calhoun, Jon Franczyk, Jason D. McClaughry, and Katherine Daniel.Title from PDF cover (viewed on February 27, 2023).This archived document is maintained by the State Library of Oregon as part of the Oregon Documents Depository Program. It is for informational purposes and may not be suitable for legal purposes.Includes bibliographical references (pages 20-24).Mode of access: Internet from the Oregon Government Publications Collection.Text in English
- …
